Tan TE, Anees A, Chen C, Li S, Xu X, Li Z, Xiao Z, Yang Y, Lei X, Ang M, Chia A, Lee SY, Wong EYM, Yeo IYS, Wong YL, Hoang QV, Wang YX, Bikbov MM, Nangia V, Jonas JB, Chen YP, Wu WC, Ohno-Matsui K, Rim TH, Tham YC, Goh RSM, Lin H, Liu H, Wang N, Yu W, Tan DTH, Schmetterer L, Cheng CY, Chen Y, Wong CW, Cheung GCM, Saw SM, Wong TY, Liu Y, and Ting DSW
Background: By 2050, almost 5 billion people globally are projected to have myopia, of whom 20% are likely to have high myopia with clinically significant risk of sight-threatening complications such as myopic macular degeneration. These are diagnoses that typically require specialist assessment or measurement with multiple unconnected pieces of equipment. Artificial intelligence (AI) approaches might be effective for risk stratification and to identify individuals at highest risk of visual loss. However, unresolved challenges for AI medical studies remain, including paucity of transparency, auditability, and traceability., Methods: In this retrospective multicohort study, we developed and tested retinal photograph-based deep learning algorithms for detection of myopic macular degeneration and high myopia, using a total of 226 686 retinal images. First we trained and internally validated the algorithms on datasets from Singapore, and then externally tested them on datasets from China, Taiwan, India, Russia, and the UK. We also compared the performance of the deep learning algorithms against six human experts in the grading of a randomly selected dataset of 400 images from the external datasets. As proof of concept, we used a blockchain-based AI platform to demonstrate the real-world application of secure data transfer, model transfer, and model testing across three sites in Singapore and China., Findings: The deep learning algorithms showed robust diagnostic performance with areas under the receiver operating characteristic curves [AUC] of 0·969 (95% CI 0·959-0·977) or higher for myopic macular degeneration and 0·913 (0·906-0·920) or higher for high myopia across the external testing datasets with available data. In the randomly selected dataset, the deep learning algorithms outperformed all six expert graders in detection of each condition (AUC of 0·978 [0·957-0·994] for myopic macular degeneration and 0·973 [0·941-0·995] for high myopia). We also successfully used blockchain technology for data transfer, model transfer, and model testing between sites and across two countries., Interpretation: Deep learning algorithms can be effective tools for risk stratification and screening of myopic macular degeneration and high myopia among the large global population with myopia. The blockchain platform developed here could potentially serve as a trusted platform for performance testing of future AI models in medicine., Funding: None., Competing Interests: Declaration of interests DSWT and TYW are co-inventors, with patents pending, for a deep learning system for diabetic retinopathy, glaucoma, and age-related macular degeneration (SG Non-Provisional Application number 10201706186V), and a computer-implemented method for training an image classifier using weakly annotated training data (SG Provisional Patent Application number 10201901083Y), and are co-founders and shareholders of EyRIS, Singapore. HLin has a patent pending for a system and method for medical data sharing using blockchain technology (distinct from the blockchain platform presented in this study; patent number CN: 202011401658.5). THR has two patents pending relating to cardiovascular and cardio-cerebrovascular disease and eye images (cardiovascular disease diagnosis assistant method and apparatus: 10–2018–0166720(KR), 10–2018–0166721(KR), 10–2018–0166722(KR), PCT/KR2018/016388; and method for predicting cardio-cerebrovascular disease using eye image: 10–2017–0175865(KR), and was a scientific advisor to and is a stockholder for Medi Whale. YLW is an employee of Essilor International. All other authors declare no competing interests., (Copyright © 2021 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC-ND 4.0 license. Published by Elsevier Ltd.. All rights reserved.)